© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67793
    Prev
    Next
    INDEX
    Explanations

    value or date

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags numeric literals (e.g. attribute values, parameters, or option numbers) appearing in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     If
    -0.97
     into
    -0.91
     xf
    -0.90
    鬟
    -0.88
     also
    -0.88
    menin
    -0.88
     Malden
    -0.87
     yaw
    -0.87
    вной
    -0.87
     Biochim
    -0.86
    POSITIVE LOGITS
    astronomie
    1.00
    Doktor
    0.97
     lesquelles
    0.96
    guiar
    0.93
    قدام
    0.92
     marrón
    0.88
    チック
    0.87
    Dati
    0.87
    ൦
    0.86
     samoz
    0.86
    Activations Density 0.007%

    No Known Activations